engineering / skill
Langfuse Skills
Agent skills that teach a coding assistant to work with Langfuse tracing, prompt management and evaluation, and to migrate from other LLM platforms.
At a glance
- Purpose
- Agent skills that teach a coding assistant to work with Langfuse tracing, prompt management and evaluation, and to migrate from other LLM platforms.
- Runs in
- Local agent with shell
- Operating systems
- Not stated
- Needs
- Runtime: Not stated; Needs internet: Yes; Needs accounts or API keys beyond your agent: Yes
- Files and data
- Reads files: Not stated; Writes files: Not stated; Sends data to other services: Yes
- Tool type
- Skill
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- According to the README, the skills are for AI coding assistants such as Claude Code and Cursor. It gives a Cursor plugin install, a skills CLI install and a manual symlink. The top-level entries include .claude-plugin, .codex-plugin and .cursor-plugin folders.
- External costs
- The repository is MIT-licensed and the README states no pricing. The skills need a Langfuse account and API keys, and the README does not say what a Langfuse account costs. Your coding agent or model provider may charge for usage.
- Permissions
- The skills act through your coding agent with the access you give it. The README shows a Cursor plugin installation, an npx skills add installation, and a manual route that clones the repository and creates a symlink in your agent's skills directory. The README says langfuse queries and manages traces, prompts, datasets and scores through the Langfuse API. The README says migrate-to-langfuse handles a live tracing cutover and transfers historical traces, datasets, prompts and evaluators. The README shows your Langfuse API keys set as environment variables.
- Usage terms
- MIT License, as stated in the repository. See its LICENSE file for the exact terms.
Code on GitHub
langfuse/skills
MITAgent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation
Topics: evaluation langfuse skill skills tracing
Public GitHub data fetched · 0 days old
Skill folders in this repository (3)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
Langfuse Skills is a set of Agent Skills for working with Langfuse, which the README describes as an open-source LLM engineering platform for tracing, prompt management and evaluation. The README names Claude Code and Cursor as example coding assistants.The README describes langfuse as the main skill for querying and managing traces, prompts, datasets and scores through the Langfuse API and looking up documentation. The README describes migrate-to-langfuse as a skill for migration from platforms such as LangSmith, Arize and Braintrust. The README says that migration skill interviews you about scope, then handles the live tracing cutover and transfer of historical traces, datasets, prompts and evaluators.
The README says an agent automatically uses these skills when relevant. Its examples include setting up tracing, setting up CI/CD experiment gates with langfuse/experiment-action, auditing instrumentation, preparing for the v4 platform migration and moving prompts to prompt management.
Who it is for
Developers who use Langfuse and want a coding assistant such as Claude Code or Cursor to help set it up, query it or migrate to it.Example tasks
Set up Langfuse tracing in a project.Set up CI/CD experiment gates with langfuse/experiment-action.
The README lists auditing existing instrumentation as a usage example.
Query traces, prompts or datasets through the Langfuse API.
Migrate from another LLM observability or evals platform to Langfuse.